You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi,
I suppose
state, done = env.reset(), False
in line 141 and 157 of rainbow main.py is to reset both agent and environment. May I ask after setting the environment will the objects location be randomized or kept in the initial position, and is there a way to reset agent's position only while keeping the environment as it is?
Thank you.
The text was updated successfully, but these errors were encountered:
I tried to use teleport to reset agent's position without affecting environment:
env.step(action='Teleport', x=0.999, y=1.01, z=-0.3541)
but got error:TypeError: step() got an unexpected keyword argument 'x'
So apparently 'env' is not the same as 'controller' in ai2thor. I'm not sure how to use controller.step(action='Teleport', x=0.999, y=1.01, z=-0.3541) in your implementation. Mind to give any advice?
It occurred to me that the current wrapper does not permit teleport. Then is there any way to save the environment setting (everything apart from the agent) and load it later?
also when I choose not to reset the environment by commenting both line 141 and 157 it gives me this error:
AttributeError: 'NoneType' object has no attribute 'metadata'
when it ran line 132:
next_state, _, done = env.step(np.random.randint(0, action_space))
Does this line just let agent make a random movement and what could be the possible reasons for the error?
Hi,
I suppose
state, done = env.reset(), False
in line 141 and 157 of rainbow main.py is to reset both agent and environment. May I ask after setting the environment will the objects location be randomized or kept in the initial position, and is there a way to reset agent's position only while keeping the environment as it is?
Thank you.
The text was updated successfully, but these errors were encountered: